Added alternatives to tdp-finder.py

Now it is possible to find the cpu power from raw details, like `/proc/cpuinfo` or the raw model name.

Author: jmfernandez

cpuinfo-tdp-finder.py

@@ -0,0 +1,24 @@
+#!/usr/bin/env python
+# -*- coding: utf-8 -*-
+
+# SPDX-License-Identifier: GPL-3.0-or-later
+# treecript, a process tree metrics gatherer.
+# Copyright (C) 2026 Barcelona Supercomputing Center, José M. Fernández
+#
+# This program is free software: you can redistribute it and/or modify
+# it under the terms of the GNU General Public License as published by
+# the Free Software Foundation, either version 3 of the License, or
+# (at your option) any later version.
+#
+# This program is distributed in the hope that it will be useful, but
+# WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+# General Public License for more details.
+#
+# You should have received a copy of the GNU General Public License
+# along with this program. If not, see <https://www.gnu.org/licenses/>.
+
+from treecript.tdp_finder import main_cpuinfo_tdp_finder
+
+if __name__ == "__main__":
+    main_cpuinfo_tdp_finder()

modelname-tdp-finder.py

@@ -0,0 +1,24 @@
+#!/usr/bin/env python
+# -*- coding: utf-8 -*-
+
+# SPDX-License-Identifier: GPL-3.0-or-later
+# treecript, a process tree metrics gatherer.
+# Copyright (C) 2026 Barcelona Supercomputing Center, José M. Fernández
+#
+# This program is free software: you can redistribute it and/or modify
+# it under the terms of the GNU General Public License as published by
+# the Free Software Foundation, either version 3 of the License, or
+# (at your option) any later version.
+#
+# This program is distributed in the hope that it will be useful, but
+# WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+# General Public License for more details.
+#
+# You should have received a copy of the GNU General Public License
+# along with this program. If not, see <https://www.gnu.org/licenses/>.
+
+from treecript.tdp_finder import main_modelname_tdp_finder
+
+if __name__ == "__main__":
+    main_modelname_tdp_finder()

setup.py

@@ -67,9 +67,11 @@
         ]
     },
     scripts=[
+        "cpuinfo-tdp-finder.py",
         "execution-metrics-collector.py",
         "process-metrics-collector.py",
         "metrics-aggregator.py",
+        "modelname-tdp-finder.py",
         "plotGraph.py",
         "tdp-finder.py",
         "execution-metrics-collector.sh",

tdp-finder.py

@@ -18,7 +18,7 @@
 # You should have received a copy of the GNU General Public License
 # along with this program. If not, see <https://www.gnu.org/licenses/>.
 
-from treecript.tdp_finder import main
+from treecript.tdp_finder import main_tdp_finder
 
 if __name__ == "__main__":
-    main()
+    main_tdp_finder()

tests/core/test_collector.py

@@ -25,7 +25,7 @@
 import subprocess
 
 from treecript.collector import execution_metrics_collector
-from treecript.tdp_finder import tdp_finder
+from treecript.tdp_finder import tdp_finder_from_series
 
 from typing import (
     TYPE_CHECKING,
@@ -88,7 +88,7 @@ def test_collector(
 
 
 @COLLECTOR_TESTBED
-def test_tdp_finder(
+def test_tdp_finder_from_series(
     tmpdir: "str",
     command_line: "Sequence[str]",
     should_fail: "Optional[Sequence[str]]",
@@ -110,7 +110,7 @@ def test_tdp_finder(
     assert processors_file.exists()
 
     try:
-        tdp_finder(metrics_path, processors_file)
+        tdp_finder_from_series(metrics_path, processors_file)
     except BaseException:
         current_frame = inspect.currentframe()
         if (

treecript/collector.py

@@ -42,7 +42,6 @@
 if TYPE_CHECKING:
     from typing import (
         Any,
-        Final,
         Mapping,
         MutableMapping,
         MutableSequence,
@@ -52,78 +51,23 @@
         Tuple,
     )
 
-    from typing_extensions import (
-        TypeAlias,
-    )
-
-    CPUInfo: TypeAlias = MutableMapping[str, Any]
-
-CPU_DETAILS_FILENAME: "Final[str]" = "cpu_details.json"
-CORE_AFFINITY_FILENAME: "Final[str]" = "core_affinity.json"
-REFERENCE_PID_FILENAME: "Final[str]" = "reference_pid.txt"
-SAMPLING_PERIOD_FILENAME: "Final[str]" = "sampling-period-seconds.txt"
-PIDS_FILENAME: "Final[str]" = "pids.txt"
-AGGREGATION_METRICS_FILENAME: "Final[str]" = "agg_metrics.tsv"
-
-METRICS_CSV_FILENAME_TEMPLATE: "Final[str]" = "metrics-{0}_{1}.csv"
-COMMAND_TXT_FILENAME_TEMPLATE: "Final[str]" = "command-{0}_{1}.txt"
-COMMAND_JSON_FILENAME_TEMPLATE: "Final[str]" = "command-{0}_{1}.json"
+from .common import (
+    AGGREGATION_METRICS_FILENAME,
+    COMMAND_JSON_FILENAME_TEMPLATE,
+    COMMAND_TXT_FILENAME_TEMPLATE,
+    CPU_DETAILS_FILENAME,
+    CORE_AFFINITY_FILENAME,
+    METRICS_CSV_FILENAME_TEMPLATE,
+    PIDS_FILENAME,
+    REFERENCE_PID_FILENAME,
+    SAMPLING_PERIOD_FILENAME,
+    parse_cpuinfo,
+)
 
 # Module level logger
 logger = logging.getLogger(__name__)
 
 
-def parse_cpuinfo(
-    cpuinfo_filename: "str" = "/proc/cpuinfo",
-) -> "Tuple[Mapping[str, CPUInfo], Mapping[str, Tuple[str, str]]]":
-    kvsplitter = re.compile(r"\s*:\s*")
-
-    entries = []
-    curr_entry: "CPUInfo" = dict()
-    cpu_hash: "MutableMapping[str, CPUInfo]" = {}
-    processor2corecpu: "MutableMapping[str, Tuple[str, str]]" = {}
-    with open(cpuinfo_filename, mode="r", encoding="latin1") as cH:
-        for line in cH:
-            line = line.rstrip("\n")
-            tokens = kvsplitter.split(line)
-            if len(tokens) < 2:
-                entries.append(curr_entry)
-                physical_id = curr_entry.get("physical id")
-                assert isinstance(physical_id, str)
-                processor = curr_entry.get("processor")
-                assert isinstance(processor, str)
-                if physical_id in cpu_hash:
-                    curr_cpu = cpu_hash[physical_id]
-                else:
-                    curr_cpu = copy.copy(curr_entry)
-                    curr_cpu["processors"] = []
-                    cpu_hash[physical_id] = curr_cpu
-                curr_cpu["processors"].append(processor)
-                core_id = curr_entry.get("core id")
-                assert isinstance(core_id, str)
-                processor2corecpu[processor] = (physical_id, core_id)
-                curr_entry = dict()
-            else:
-                curr_entry[tokens[0]] = tokens if len(tokens) > 2 else tokens[1]
-    if curr_entry:
-        entries.append(curr_entry)
-        physical_id = curr_entry.get("physical id")
-        assert isinstance(physical_id, str)
-        processor = curr_entry.get("processor")
-        assert isinstance(processor, str)
-        if physical_id in cpu_hash:
-            curr_cpu = cpu_hash[physical_id]
-        else:
-            curr_cpu = copy.copy(curr_entry)
-            curr_cpu["processors"] = []
-        curr_cpu["processors"].append(processor)
-        core_id = curr_entry.get("core id")
-        assert isinstance(core_id, str)
-        processor2corecpu[processor] = (physical_id, core_id)
-
-    return cpu_hash, processor2corecpu
-
-
 def analyse_list_of_processes(
     children: "Sequence[psutil.Process]",
     processor2corecpu: "Mapping[str, Tuple[str, str]]",